[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: re-running same regression (xtreg, fe) and getting different answers
I am re-running the same program that I used to generate the regression
output for a paper I wrote in June and I am getting slightly
different answer after the command xtreg, fe. For instance, a coefficient
that was 22.68 now becomes 22.54 (the t-value changing
from 2.67 to 2.65). The number of observations
and the summary statistics have not changed from what I have in the paper. I
am using stata 7 but I periodically do the official updates.
My question is, is it possible that the changes in coefficients of this
order of magnitude was caused by an updating of Stata?
(in case this matters, the regression has 5101 observations, 37 explanatory
variables, and 561 fixed effects).
Associate Professor of Economics
University of Alabama
Culverhouse College of Commerce & Business Administration
Tuscaloosa, AL 35487-002
205-348-8967, fax 205-348-0590
* For searches and help try: